Model comparison
Deepseek Coder v2 vs GLM-4.6V
GLM-4.6V is the stronger model overall, scoring 41.3 to 35.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GLM-4.6V in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6V leads 56.6 to 38.2.
Side by side
| Deepseek Coder v2 | GLM-4.6V | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 35.9 | 41.3 |
| Released | 2024-06-17 | 2025-12-08 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $0.90 |
| Results tracked | 24 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6V leads
Deepseek Coder v2: 38.1 (#183), GLM-4.6V: 40.9 (#128)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1251 | 1390 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning GLM-4.6V leads
Deepseek Coder v2: 23.6 (#176), GLM-4.6V: 27.6 (#115)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1368 |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), GLM-4.6V: —
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge GLM-4.6V leads
Deepseek Coder v2: 32.3 (#212), GLM-4.6V: 38.0 (#149)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Expert | 1181 | 1371 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, GLM-4.6V: 34.8 (#90)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
Multilingual GLM-4.6V leads
Deepseek Coder v2: 36.3 (#240), GLM-4.6V: 48.6 (#141)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1182 | 1359 |
| LMArena Chinese | 1201 | 1425 |
| LMArena Russian | 1188 | 1340 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following GLM-4.6V leads
Deepseek Coder v2: 61.7 (#242), GLM-4.6V: 71.4 (#151)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1180 | 1352 |
Long Context GLM-4.6V leads
Deepseek Coder v2: 37.0 (#224), GLM-4.6V: 41.3 (#143)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1219 | 1358 |
Writing & Preference GLM-4.6V leads
Deepseek Coder v2: 38.2 (#253), GLM-4.6V: 56.6 (#137)
| Benchmark | Deepseek Coder v2 | GLM-4.6V |
|---|---|---|
| LMArena Text | 1191 | 1377 |
| LMArena Creative Writing | 1120 | 1347 |
| LMArena Multi-Turn | 1177 | 1360 |
Frequently asked questions
Is Deepseek Coder v2 better than GLM-4.6V?
GLM-4.6V is the stronger model overall, scoring 41.3 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or GLM-4.6V better for coding?
GLM-4.6V scores higher on coding benchmarks: 40.9 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and GLM-4.6V share?
11 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GLM-4.6V has 12.